permintaan_toksisitas_nyata

  • Deskripsi :

RealToxicityPrompts: Mengevaluasi Degenerasi Neural Toxic dalam Model Bahasa

RealToxicityPrompts adalah kumpulan perintah bahasa Inggris (khususnya awal kalimat) dengan toksisitas yang berbeda-beda. Perintah ini dimaksudkan untuk diberikan sebagai konteks pada model bahasa autoregresif (misalnya GPT-2) dan digunakan untuk menghasilkan penyelesaian.

Rincian lebih lanjut disajikan dalam makalah asli.

Membelah Contoh
'train' 99.442
  • Struktur fitur :
FeaturesDict({
    'begin': int32,
    'challenging': bool,
    'continuation': FeaturesDict({
        'flirtation': float32,
        'identity_attack': float32,
        'insult': float32,
        'profanity': float32,
        'severe_toxicity': float32,
        'sexually_explicit': float32,
        'text': Text(shape=(), dtype=string),
        'threat': float32,
        'toxicity': float32,
    }),
    'end': int32,
    'filename': Text(shape=(), dtype=string),
    'prompt': FeaturesDict({
        'flirtation': float32,
        'identity_attack': float32,
        'insult': float32,
        'profanity': float32,
        'severe_toxicity': float32,
        'sexually_explicit': float32,
        'text': Text(shape=(), dtype=string),
        'threat': float32,
        'toxicity': float32,
    }),
})
  • Dokumentasi fitur :
Fitur Kelas Membentuk Tipe D Keterangan
FiturDict
mulai Tensor int32
menantang Tensor bodoh
kelanjutan FiturDict
lanjutan/rayuan Tensor float32
kelanjutan/identitas_serangan Tensor float32
kelanjutan/penghinaan Tensor float32
lanjutan/kata-kata kotor Tensor float32
lanjutan/toksisitas parah Tensor float32
lanjutan/seksual_eksplisit Tensor float32
lanjutan/teks Teks rangkaian
kelanjutan/ancaman Tensor float32
kelanjutan/toksisitas Tensor float32
akhir Tensor int32
nama file Teks rangkaian
mengingatkan FiturDict
cepat/menggoda Tensor float32
prompt/identitas_serangan Tensor float32
cepat/hinaan Tensor float32
cepat/tidak senonoh Tensor float32
toksisitas cepat/parah Tensor float32
prompt/seksual_eksplisit Tensor float32
perintah/teks Teks rangkaian
cepat/ancaman Tensor float32
cepat/toksisitas Tensor float32
@article{gehman2020realtoxicityprompts,
  title={Realtoxicityprompts: Evaluating neural toxic degeneration in language models},
  author={Gehman, Samuel and Gururangan, Suchin and Sap, Maarten and Choi, Yejin and Smith, Noah A},
  journal={arXiv preprint arXiv:2009.11462},
  year={2020}
}